{"id":"https://openalex.org/W4317036142","doi":"https://doi.org/10.1145/3578553","title":"KenSwQuAD\u2014A Question Answering Dataset for Swahili Low-resource Language","display_name":"KenSwQuAD\u2014A Question Answering Dataset for Swahili Low-resource Language","publication_year":2023,"publication_date":"2023-01-17","ids":{"openalex":"https://openalex.org/W4317036142","doi":"https://doi.org/10.1145/3578553"},"language":"en","primary_location":{"id":"doi:10.1145/3578553","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578553","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3578553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014764462","display_name":"Barack Wanjawa","orcid":"https://orcid.org/0000-0003-0198-3179"},"institutions":[{"id":"https://openalex.org/I12859529","display_name":"University of Nairobi","ror":"https://ror.org/02y9nww90","country_code":"KE","type":"education","lineage":["https://openalex.org/I12859529"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Barack W. Wanjawa","raw_affiliation_strings":["University of Nairobi, Nairobi, Kenya"],"raw_orcid":"https://orcid.org/0000-0003-0198-3179","affiliations":[{"raw_affiliation_string":"University of Nairobi, Nairobi, Kenya","institution_ids":["https://openalex.org/I12859529"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041771996","display_name":"Lilian Wanzare","orcid":"https://orcid.org/0000-0002-6718-900X"},"institutions":[{"id":"https://openalex.org/I195610458","display_name":"Maseno University","ror":"https://ror.org/023pskh72","country_code":"KE","type":"education","lineage":["https://openalex.org/I195610458"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Lilian D. A. Wanzare","raw_affiliation_strings":["Maseno University, Maseno, Kenya"],"raw_orcid":"https://orcid.org/0000-0002-6718-900X","affiliations":[{"raw_affiliation_string":"Maseno University, Maseno, Kenya","institution_ids":["https://openalex.org/I195610458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068463664","display_name":"Florence Indede","orcid":"https://orcid.org/0000-0003-4285-770X"},"institutions":[{"id":"https://openalex.org/I195610458","display_name":"Maseno University","ror":"https://ror.org/023pskh72","country_code":"KE","type":"education","lineage":["https://openalex.org/I195610458"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Florence Indede","raw_affiliation_strings":["Maseno University, Maseno, Kenya"],"raw_orcid":"https://orcid.org/0000-0003-4285-770X","affiliations":[{"raw_affiliation_string":"Maseno University, Maseno, Kenya","institution_ids":["https://openalex.org/I195610458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045469425","display_name":"Owen McOnyango","orcid":"https://orcid.org/0000-0002-1276-0395"},"institutions":[{"id":"https://openalex.org/I195610458","display_name":"Maseno University","ror":"https://ror.org/023pskh72","country_code":"KE","type":"education","lineage":["https://openalex.org/I195610458"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Owen Mconyango","raw_affiliation_strings":["Maseno University, Maseno, Kenya"],"raw_orcid":"https://orcid.org/0000-0002-1276-0395","affiliations":[{"raw_affiliation_string":"Maseno University, Maseno, Kenya","institution_ids":["https://openalex.org/I195610458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014319170","display_name":"Lawrence Muchemi","orcid":"https://orcid.org/0000-0001-5911-5679"},"institutions":[{"id":"https://openalex.org/I12859529","display_name":"University of Nairobi","ror":"https://ror.org/02y9nww90","country_code":"KE","type":"education","lineage":["https://openalex.org/I12859529"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Lawrence Muchemi","raw_affiliation_strings":["University of Nairobi, Nairobi, Kenya"],"raw_orcid":"https://orcid.org/0000-0001-5911-5679","affiliations":[{"raw_affiliation_string":"University of Nairobi, Nairobi, Kenya","institution_ids":["https://openalex.org/I12859529"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071646145","display_name":"Edward Ombui","orcid":"https://orcid.org/0000-0002-1787-0681"},"institutions":[{"id":"https://openalex.org/I4210165634","display_name":"Africa Nazarene University","ror":"https://ror.org/05twfp995","country_code":"KE","type":"education","lineage":["https://openalex.org/I4210165634"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Edward Ombui","raw_affiliation_strings":["Africa Nazarene University, Nairobi, Kenya"],"raw_orcid":"https://orcid.org/0000-0002-1787-0681","affiliations":[{"raw_affiliation_string":"Africa Nazarene University, Nairobi, Kenya","institution_ids":["https://openalex.org/I4210165634"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4474,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90808072,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"22","issue":"4","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8229219913482666},{"id":"https://openalex.org/keywords/swahili","display_name":"Swahili","score":0.7884136438369751},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7462437152862549},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6371524930000305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.535027265548706},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.47698599100112915},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47483211755752563},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41338396072387695},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3239947259426117},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21763485670089722},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07509028911590576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229219913482666},{"id":"https://openalex.org/C2779913364","wikidata":"https://www.wikidata.org/wiki/Q7838","display_name":"Swahili","level":2,"score":0.7884136438369751},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7462437152862549},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6371524930000305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535027265548706},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.47698599100112915},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47483211755752563},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41338396072387695},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3239947259426117},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21763485670089722},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07509028911590576},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3578553","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578553","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2205.02364","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.02364","pdf_url":"https://arxiv.org/pdf/2205.02364","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3578553","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578553","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1663984431","https://openalex.org/W1971460269","https://openalex.org/W2091746061","https://openalex.org/W2183047366","https://openalex.org/W2250539671","https://openalex.org/W2251818205","https://openalex.org/W2315995013","https://openalex.org/W2621264094","https://openalex.org/W2901059163","https://openalex.org/W2950251328","https://openalex.org/W2953151445","https://openalex.org/W2963748441","https://openalex.org/W2999905431","https://openalex.org/W3213234281","https://openalex.org/W4287854589"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2805599431","https://openalex.org/W2361152157","https://openalex.org/W2351286801","https://openalex.org/W207304934","https://openalex.org/W4377703168","https://openalex.org/W2123793327","https://openalex.org/W15319282","https://openalex.org/W1560657467","https://openalex.org/W2296730655"],"abstract_inverted_index":{"The":[0,89,109],"need":[1,76],"for":[2,58,64,173],"question-answering":[3,83],"(QA)":[4],"datasets":[5,55],"in":[6,44,48,86,127],"low-resource":[7,38],"languages":[8,107],"is":[9,29,41],"the":[10,17,20,52,81,102,115,142,147,160,163,168,183],"motivation":[11],"of":[12,19,35,51,61,131,139,141,156,182],"this":[13,87],"research,":[14],"leading":[15],"to":[16,93,162,180],"development":[18],"Kencorpus":[21,103],"Swahili":[22,98,184],"Question":[23],"Answering":[24],"Dataset":[25],"(KenSwQuAD).":[26],"This":[27],"dataset":[28,130,169],"annotated":[30,111,143],"from":[31,97,114],"raw":[32],"story":[33],"texts":[34,99,113,118,144],"Swahili,":[36],"a":[37,105,128],"language":[39,63],"that":[40,146,167],"predominantly":[42],"spoken":[43],"eastern":[45],"Africa":[46],"and":[47,70],"other":[49],"parts":[50],"world.":[53],"Question-answering":[54],"are":[56],"important":[57],"machine":[59],"comprehension":[60],"natural":[62],"tasks":[65],"such":[66,79,174],"as":[67,80],"internet":[68],"search":[69],"dialog":[71],"systems.":[72],"Machine":[73],"learning":[74],"systems":[75],"training":[77],"data":[78],"gold-standard":[82],"set":[84,138,161],"developed":[85],"research.":[88],"research":[90],"engaged":[91],"annotators":[92],"formulate":[94],"QA":[95,123,133,148,164],"pairs":[96,124,149],"collected":[100],"by":[101],"project,":[104],"Kenyan":[106],"corpus.":[108],"project":[110],"1,445":[112],"total":[116],"2,585":[117],"with":[119],"at":[120],"least":[121],"5":[122],"each,":[125],"resulting":[126],"final":[129],"7,526":[132],"pairs.":[134],"A":[135,154],"quality":[136],"assurance":[137],"12.5%":[140],"confirmed":[145,166],"were":[150],"all":[151],"correctly":[152],"annotated.":[153],"proof":[155],"concept":[157],"on":[158],"applying":[159],"task":[165],"can":[170],"be":[171],"usable":[172],"tasks.":[175],"KenSwQuAD":[176],"has":[177],"also":[178],"contributed":[179],"resourcing":[181],"language.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
